What the agent did
Every three hours a bot checks his sites for new articles, writes copy per platform and queues it for publishing through Zernio. Another reads and triages two Google Workspace inboxes through the browser, including the spam folder, and drafts replies. Another builds invoices from forwarded client emails using PayPal and Wise. A fourth pulls client numbers through the Semrush MCP server or dashboards and drafts report commentary.
Result, as claimed
Fakhri says the four workflows give back 35 hours a week. He puts the social workflow at about 5 hours a week and the invoicing one at "the most annoying hour of my week". He says the bot found 48 real messages in spam in the first month, including a network approval he had chased for two weeks. He says it cost twenty dollars to start.
This is the result as claimed in the public source linked below. It has not been checked and is not a typical outcome.
Proof
Try it yourself
Have an agent check your business spam folder each week for real client, partner and payment mail, and draft replies you send yourself.
Prompt
Check the spam folder of my [business email] for the last [7] days. My clients, partners and payment platforms are: [list]. For each message, give the date, sender, subject and a label, Likely real or Likely spam, with one reason. Treat as Likely real anything from my list, any reply to a thread I started, and any notice about an invoice, payout, approval or contract. Do not open links or attachments. Do not move, delete or reply to anything. Draft a short reply for each Likely real message that needs one and leave it unsent. End with senders I may want to mark as safe. Return a draft only. Never send, spend, change settings or write to a live system.
Prompt: starter by Solopreneur Code
Tools
- Grok Bot Named in the source. Official URL not checked in intake, omitted. No approved affiliate.
- Gmail Named in the source. Many mail connectors only see the inbox, so pasting spam headers works too.
Steps
- Give the agent read-only access to the inbox, or paste sender, subject, date and first lines of each spam message.
- Fill in the brackets and run the prompt once a week.
- Open each Likely real message in your own mail app and check the sender domain.
- Send any reply yourself and mark safe senders yourself.
Watch out: Spam folders hold phishing. A Likely real label can be wrong, so confirm the sender domain yourself before replying, paying or clicking anything.
Starter version by Solopreneur Code
Skill: Customer replies
Add this skill
Spam folder rescue check
Checks your business spam folder for real client, partner and payment mail, labels each message and drafts replies you send yourself.
- Works with
- Claude, ChatGPT, Gemini, Grok Bot, Any AI chat Not tested. Reading spam directly needs an agent that can open the spam folder, which the source says many connectors cannot. Any AI chat works on pasted headers.
- Tools in the story
- Grok Bot, Gmail
- Country
- Country unknown
How to use this: Copy the skill, paste it into Claude, ChatGPT or Gemini, and ask it to save it as a skill. If it cannot, it will still follow the steps.
Show skill
If the Copy button does not work, select this text and copy it.